| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.244646333549643, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.837767683322518e-05, | |
| "loss": 0.1601, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.6755353666450355e-05, | |
| "loss": 0.0226, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.5133030499675535e-05, | |
| "loss": 0.0105, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.3510707332900715e-05, | |
| "loss": 0.0054, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.1888384166125895e-05, | |
| "loss": 0.0084, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.0266060999351075e-05, | |
| "loss": 0.0071, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.864373783257625e-05, | |
| "loss": 0.0055, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.702141466580143e-05, | |
| "loss": 0.0024, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 3.539909149902661e-05, | |
| "loss": 0.0054, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.377676833225179e-05, | |
| "loss": 0.0043, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.215444516547697e-05, | |
| "loss": 0.0065, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.053212199870215e-05, | |
| "loss": 0.0046, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.890979883192732e-05, | |
| "loss": 0.0015, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.72874756651525e-05, | |
| "loss": 0.0015, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 2.5665152498377677e-05, | |
| "loss": 0.0005, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.4042829331602857e-05, | |
| "loss": 0.0011, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.2420506164828034e-05, | |
| "loss": 0.0032, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2.0798182998053214e-05, | |
| "loss": 0.003, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.9175859831278394e-05, | |
| "loss": 0.0017, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 1.755353666450357e-05, | |
| "loss": 0.0017, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 15410, | |
| "num_train_epochs": 5, | |
| "total_flos": 1496781631024068.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |